INDEX

Explanations

references to programming concepts and data structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

data tables

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 صوتيه

-0.62

évaluateur

-0.62

yntaxException

-0.59

transQ

-0.59

recated

-0.59

ynchronously

-0.58

WebVitals

-0.57



-0.57

IKit

-0.56

Chham

-0.56

POSITIVE LOGITS

TypedDataSet

0.77

DataTable

0.52

 DataTable

0.51

Data

0.50

 Data

0.49

data

0.48

 data

0.48

dataTable

0.44

datatable

0.43

 Datas

0.42

Activations Density 0.000%

references to programming concepts and data structures

data tables

No Comments

No Known Activations